[build-system]
requires = ["setuptools>=64", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "khaosz_dataset"
version = "0.1.0"
description = "A dataset processing toolkit for language model training"
readme = "README.md"
requires-python = ">=3.10"
dependencies = [
    "tokenizers>=0.13.0",
    "datasets>=2.10.0",
    "numpy>=1.21.0",
    "tqdm>=4.64.0",
    "torch>=2.1.0",
    "h5py>=3.7.0",
    "regex>=2022.03.15"
]
keywords = ["nlp", "datasets", "language-models", "machine-learning"]
[project.urls]
Homepage = "https://github.com/khaosz/khaosz_dataset"

[tool.setuptools.packages.find]
where = ["."]